mlsanityData to 7 Oct 2026

Explaining Deep Face Algorithms through Visualization: A Survey

arXiv 2309.14715 ↗First posted 26 Sep 2023cs.CV cs.HC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Although current deep models for face tasks surpass human performance on some benchmarks, we do not understand how they work. Thus, we cannot predict how it will react to novel inputs, resulting in catastrophic failures and unwanted biases in the algorithms. Explainable AI helps bridge the gap, but currently, there are very few visualization algorithms designed for faces. This work undertakes a first-of-its-kind meta-analysis of explainability algorithms in the face domain. We explore the nuances and caveats of adapting general-purpose visualization algorithms to the face domain, illustrated by computing visualizations on popular face models. We review existing face explainability works and reveal valuable insights into the structure and hierarchy of face networks. We also determine the design considerations for practical face visualizations accessible to AI practitioners by conducting a user study on the utility of various explainability algorithms.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 47 of its 87 references that are in the map. First posted on arXiv 26 Sep 2023.

Builds on

47 of 87 references.

References · 47

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  9. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  10. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  11. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  12. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
35 more
  1. 2018Sanity Checks for Saliency Mapscited by 1,149
  2. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  3. 2017Deep Image Priorcited by 1,097
  4. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  6. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  7. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  8. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  9. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  10. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  11. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  12. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
  13. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  14. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  15. 2020A Survey on Neural Network Interpretabilitycited by 291
  16. 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
  17. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  18. 2016Synthesizing the preferred inputs for neurons in neural networks via deep generator networkscited by 181
  19. 2015Inverting Visual Representations with Convolutional Networkscited by 168
  20. 2017The Shattered Gradients Problem: If resnets are the answer, then what is the question?cited by 156
  21. 2018Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networkscited by 128
  22. 2016Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networkscited by 106
  23. 2017Interpreting Deep Visual Representations via Network Dissectioncited by 103
  24. 2019Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Surveycited by 93
  25. 2017Face Aging With Conditional Generative Adversarial Networkscited by 51
  26. 2020Explainable Face Recognitioncited by 34
  27. 2018Towards Interpretable Face Recognitioncited by 30
  28. 2015Understanding Intra-Class Knowledge Inside CNNcited by 22
  29. 2018Visual Psychophysics for Making Face Recognition Algorithms More Explainablecited by 19
  30. 2016PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognitioncited by 18
  31. 2019Are Self-Driving Cars Secure? Evasion Attacks against Deep Neural Networks for Steering Angle Predictioncited by 16
  32. 2021Sanity Simulations for Saliency Methodscited by 15
  33. 2021A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networkscited by 14
  34. 2022Perception Visualization: Seeing Through the Eyes of a DNNcited by 5
  35. 2021Canonical Saliency Maps: Decoding Deep Face Modelscited by 2

Built on by

Not cited yet.